Backtesting
Exceedance-based backtesting of expected shortfall
The authors apply exceedance-based validation techniques often used for VaR model validation the the validation of ES models, showing such an application to be feasible.
BNPP, Deutsche among EU banks hit by VAR breaches in April
Sharpest rise in backtesting exceptions since 2022 Ukraine war shock largely linked to tariff chaos
Why know-it-all LLMs make second-rate forecasters
A bevy of experiments suggests LLMs are ill-suited for time-series forecasting
US banks notch most VAR overshoots since pandemic
Dealers’ gauges underestimated trading inventory price swings on 34 occasions during Q2
Barclays logs five VAR breaches amid tariff turmoil
Bank’s regulatory VAR model loses green status for the first time since 2018
Double VAR breach in Q2 adds $4.1bn to JP Morgan’s market RWAs
Sixth regulatory backtesting exception in nine months lifts the multiplier above minimum for the first time since Q3 2022
Semiparametric GARCH models for value-at-risk and expected shortfall: an object-driven procedure
Basing their approach in object-drive smoothing, the authors calculate value-at-risk and expected shortfall via an application of semi-GARCH models.
US banks’ VAR shortfalls are wrapped in a black box
Public disclosures only allow crude approximations of loss size and timing
The VAR-centric models that never were
Often spotlighted, rarely dominant – VAR plays a surprisingly small role in most IMA stacks
Barclays takes selective approach to FRTB IMA applications
Risk Live: UK bank is applying for approval for parts of its portfolio most likely to pass approval tests
‘I feel like a guinea pig’ – lessons from an early IMA adopter
Risk Live: Nomura’s Epperlein urges flexible approach to backtesting exceptions
Overcoming issues with time-scaling value-at-risk
The authors investigate the impact of different time-scaling techniques on the accuracy of value-at- risk models, emphasising the importance of carefully scaling methods and considering alternative risk modeling approaches.
Gaussian GenAI: synthetic market data generation
A method to generate financial time series with mixture models is presented
JP Morgan’s VAR limits blown twice during haywire Q1
Breaches add to the two regulatory backtesting exceptions sustained the previous quarter
Tariff turbulence piles pressure on banks’ VAR models
Backtesting breaches start to mount, but too early to tell if regulatory intervention needed
Trading desks want regulators to face down the NMRF monster
Rule-makers in Australia and the European Union are open to changes to the unpopular FRTB test
UniCredit tops Europe’s VAR breach leaderboard in 2024
Swedbank, Commerzbank and SocGen among model users repeatedly blindsided by volatility
Market knee-jerks keep VAR models on their toes
With a return to volatility, increased backtesting exceptions show banks’ algos are stretched
US dealers tally most VAR breaches since mid-2023
Market turmoil in Q4 blindsides models at systemic and regional banks alike
Buffer stop: Eurex clearing members shunt default fund
Clearing house’s CRO says both members and clients opt to pay more margin instead
During Trump turbulence, value-at-risk may go pop
Trading risk models have been trained in quiet markets, and volatility is now looming